© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208513
    Prev
    Next
    INDEX
    Explanations

    kq calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    款式
    0.49
     prematurely
    0.47
     россий
    0.45
     economist
    0.45
     niez
    0.45
     wedi
    0.45
    **.
    0.45
     фі
    0.44
     corrupted
    0.44
     catast
    0.44
    POSITIVE LOGITS
    u
    0.59
     आप
    0.50
     Riders
    0.47
     Nf
    0.45
    gren
    0.45
    堇
    0.45
    uq
    0.44
    Amino
    0.44
    ll
    0.43
    vall
    0.43
    Activations Density 0.000%

    No Known Activations